Information Services banner Edinburgh Research Archive The University of Edinburgh crest

Edinburgh Research Archive >
Centre for Speech Technology Research >
CSTR publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1842/1266

This item has been viewed 11 times in the last year. View Statistics

Files in This Item:

File Description SizeFormat
hess_et_al.pdf288.07 kBAdobe PDFView/Open
hess_et_al.ps371.23 kBPostscriptView/Open
Title: Prosodic modules for speech recognition and understanding in VERBMOBIL.
Authors: Hess, Wolfgang
Batliner, A
Kießling, A
Kompe, R
Nöth, E
Petzold, A
Reyelt, M
Strom, Volker
Issue Date: 1995
Citation: In Norio Higuchi Yoshinori Sagisaka, Nick Campbell, editor, Computing Prosody, pages Part IV, Chapter 23, pp. 363 - 383. Springer-Verlag, New York, 1995.
Publisher: Springer-Verlag, New York.
Abstract: Within VERMOBIL, a large project on spoken language research in Germany, two modules for detecting and recognising prosodic events have been deveopled. One module operates on speech signal parameterss and the word hypothesis graph, whereas the other module, designed for a novel, highly interactive architecture, only uses speech signal parameters as its input. Phase boundaries, sentence modality, and accents are detected. The recognition rates in spontaneous dialogs are for accents up to 82.5%, for phase boundaries up to 91.7%.
URI: http://hdl.handle.net/1842/1266
Appears in Collections:CSTR publications

Items in ERA are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Valid XHTML 1.0! Unless explicitly stated otherwise, all material is copyright © The University of Edinburgh 2013, and/or the original authors. Privacy and Cookies Policy